The multivariate statistical techniques, principal component analysis, Q-modefactor analysis, correspondence analysis and fuzzy C-means clustering were applied to analyzing thedatasets of minor element concentrations ...The multivariate statistical techniques, principal component analysis, Q-modefactor analysis, correspondence analysis and fuzzy C-means clustering were applied to analyzing thedatasets of minor element concentrations in sediment samples of a core collected from the outershelf of the East China Sea. According to the analysis results, the sediment core Q43 can be dividedinto three strata with different features in minor elements. The first stratum (unit Ⅰ) ischaracterized by higher concentrations of Ⅴ, Cr, Cd and Sc, which are active and inactive elements.The second stratum (unit Ⅱ) is controlled by ultrastable elements Ⅴ, Ti, Cr, Th, Sc, Pb, etc. Thethird stratum (unit Ⅲ) is dominated by Ni, Co, Ba, Rb and Mn, which are authigenic andvolcanogenic elements. The geochemical features of the core Q43 show environmental changes in thedepositional process from the Late Pleistocene to Holocene.展开更多
Finding out out-of-vocabulary words is an urgent and difficult task in Chinese words segmentation. To avoid the defect causing by offline training in the traditional method, the paper proposes an improved prediction b...Finding out out-of-vocabulary words is an urgent and difficult task in Chinese words segmentation. To avoid the defect causing by offline training in the traditional method, the paper proposes an improved prediction by partical match （PPM） segmenting algorithm for Chinese words based on extracting local context information, which adds the context information of the testing text into the local PPM statistical model so as to guide the detection of new words. The algorithm focuses on the process of online segmentatien and new word detection which achieves a good effect in the close or opening test, and outperforms some well-known Chinese segmentation system to a certain extent.展开更多
A feature extraction, which means extracting the representative words from a text, is an important issue in text mining field. This paper presented a new Apriori and N-gram based Chinese text feature extraction method...A feature extraction, which means extracting the representative words from a text, is an important issue in text mining field. This paper presented a new Apriori and N-gram based Chinese text feature extraction method, and analyzed its correctness and performance. Our method solves the question that the exist extraction methods cannot find the frequent words with arbitrary length in Chinese texts. The experimental results show this method is feasible.展开更多
This paper presents a methodology for off-line handwritten Chinese character recognition based on mergence of consecutive segments of adaptive duration. The handwritten Chinese character string is partitioned into a s...This paper presents a methodology for off-line handwritten Chinese character recognition based on mergence of consecutive segments of adaptive duration. The handwritten Chinese character string is partitioned into a sequence of consecutive segments, which are combined to implement dissimilarity evaluation within a sliding window whose durations are determined adaptively by the integration of shapes and context of evaluations. The average stroke width is estimated for the handwritten Chinese character string, and a set of candidate character segmentation boundaries is found by using the integration of pixel and stroke features. The final decisions on segmentation and recognition are made under minimal arithmetical mean dissimilarities. Experiments proved that the proposed approach of adaptive duration outperforms the method of fixed duration, and is very effective for the recognition of overlapped, broken, touched, loosely configured Chinese characters.展开更多
Objective In tongue diagnosis,the location,color,and distribution of spots can be used to speculate on the viscera and severity of the heat evil.This work focuses on the image analysis method of artificial intelligenc...Objective In tongue diagnosis,the location,color,and distribution of spots can be used to speculate on the viscera and severity of the heat evil.This work focuses on the image analysis method of artificial intelligence(AI)to study the spotted tongue recognition of traditional Chinese medicine(TCM).Methods A model of spotted tongue recognition and extraction is designed,which is based on the principle of image deep learning and instance segmentation.This model includes multiscale feature map generation,region proposal searching,and target region recognition.Firstly,deep convolution network is used to build multiscale low-and high-abstraction feature maps after which,target candidate box generation algorithm and selection strategy are used to select high-quality target candidate regions.Finally,classification network is used for classifying target regions and calculating target region pixels.As a result,the region segmentation of spotted tongue is obtained.Under non-standard illumination conditions,various tongue images were taken by mobile phones,and experiments were conducted.Results The spotted tongue recognition achieved an area under curve(AUC)of 92.40%,an accuracy of 84.30%with a sensitivity of 88.20%,a specificity of 94.19%,a recall of 88.20%,a regional pixel accuracy index pixel accuracy(PA)of 73.00%,a mean pixel accuracy(m PA)of73.00%,an intersection over union(Io U)of 60.00%,and a mean intersection over union(mIo U)of 56.00%.Conclusion The results of the study verify that the model is suitable for the application of the TCM tongue diagnosis system.Spotted tongue recognition via multiscale convolutional neural network(CNN)would help to improve spot classification and the accurate extraction of pixels of spot area as well as provide a practical method for intelligent tongue diagnosis of TCM.展开更多
The Kunlun Fault, an active fault on the border between the Bayan Har and Kunlun-Qaidam blocks, is one of the major left lateral strike-slip faults in the Tibetan Plateau. Previous research has not reached a consensus...The Kunlun Fault, an active fault on the border between the Bayan Har and Kunlun-Qaidam blocks, is one of the major left lateral strike-slip faults in the Tibetan Plateau. Previous research has not reached a consensus on agreeable slip rates along much of its length and the slip rate gradient along the eastern part, both of which play critical roles in a range of models for the eastward extrusion and thickened crust of the Tibetan Plateau. New slip rates have been determined at sites along the eastern part of the Kunlun Fault by dating deposits and measuring atop displaced fluvial terrace risers. Field investigations and interpretation of satellite images reveal geometrical features of the fault and the late Quaternary offset, new earthquake ruptures and surface-rupturing segmentation, from which long-term slip rates and earthquake recurrence intervals on the fault are estimated. The tectonic geomorphology method has determined that the long-term horizontal slip rates on the Tuosuohu, Maqin and Ma- qu segments from west to east are 11.2±1, 9.3±2, and 4.9±1.3 mm/a while their vertical slip rates are 1.2±0.2, 0.7±0.1, and 0.3 mm/a in the late Quaternary. Results indicate that the slip rates regularly decrease along the eastern -300 km of the fault from 〉10 to 〈5 mm/a. This is consistent with the decrease in the gradient such that at the slip rate break point is at the triple point intersection with the transverse fault, which in turn is transformed to the Awancang Fault. The vector decomposition for this tectonic transformation shows that the western and eastern branches of the Awancang Fault fit the slip-partitioning mode. The slip rate of the southwestern wall is 4.6 mm/a relative to the northeastern wall and the slip direction is 112.1°. The mid-eastern part of the Kunlun Fault can be divided into three independent segments by the A＇nyemaqen double restraining bend and the Xigongzhou intersection zone, which compose the surface rupture segmentation indicators for themselves as well as the ending point of the 1937 M7.5 Tuosuohu earthquake. The average recurrence interval of the characteristic earthquakes are estimated to be 500-1000 a, respectively. The latest earthquake ruptures occurred in AD 1937 on the western Tuosuohu segment, as compared to -514-534 a BP on the Maqin segment, and -1055 to 1524 a BP on the Maqu segment. This may indicate a unidirectional migration for surface rupturing earthquakes along the mid-eastern Kunlun Fault related to stress triggered between these segments. Meanwhile, the long-term slip rate is obtained through the single event offset and the recurrence interval, which turn out to be the same results as those determined by the offset tectonic geomorphology method, i.e., the decreasing gradient corresponds to the geometrical bending and the fault＇s intersection with the transverse fault. Therefore, the falling slip rate gradient of the mid-eastern Kunlun Fault is mainly caused by eastward extension of the fault and its intersection with the transverse fault.展开更多
Automatic translation of Chinese text to Chinese Braille is important for blind people in China to acquire information using computers or smart phones. In this paper, a novel scheme of Chinese-Braille translation is p...Automatic translation of Chinese text to Chinese Braille is important for blind people in China to acquire information using computers or smart phones. In this paper, a novel scheme of Chinese-Braille translation is proposed. Under the scheme, a Braille word segmentation model based on statistical machine learning is trained on a Braille corpus, and Braille word segmentation is carried out using the statistical model directly without the stage of Chinese word segmentation. This method avoids establishing rules concerning syntactic and semantic information and uses statistical model to learn the rules stealthily and automatically. To further improve the performance, an algorithm of fusing the results of Chinese word segmentation and Braille word segmentation is also proposed. Our results show that the proposed method achieves accuracy of 92.81% for Braille word segmentation and considerably outperforms current approaches using the segmentation-merging scheme.展开更多
基金funded by the National Natural Science Foundation(Nos.40176014 and 40067013).
文摘The multivariate statistical techniques, principal component analysis, Q-modefactor analysis, correspondence analysis and fuzzy C-means clustering were applied to analyzing thedatasets of minor element concentrations in sediment samples of a core collected from the outershelf of the East China Sea. According to the analysis results, the sediment core Q43 can be dividedinto three strata with different features in minor elements. The first stratum (unit Ⅰ) ischaracterized by higher concentrations of Ⅴ, Cr, Cd and Sc, which are active and inactive elements.The second stratum (unit Ⅱ) is controlled by ultrastable elements Ⅴ, Ti, Cr, Th, Sc, Pb, etc. Thethird stratum (unit Ⅲ) is dominated by Ni, Co, Ba, Rb and Mn, which are authigenic andvolcanogenic elements. The geochemical features of the core Q43 show environmental changes in thedepositional process from the Late Pleistocene to Holocene.
基金National Natural Science Foundation of China ( No.60903129)National High Technology Research and Development Program of China (No.2006AA010107, No.2006AA010108)Foundation of Fujian Province of China (No.2008F3105)
文摘Finding out out-of-vocabulary words is an urgent and difficult task in Chinese words segmentation. To avoid the defect causing by offline training in the traditional method, the paper proposes an improved prediction by partical match （PPM） segmenting algorithm for Chinese words based on extracting local context information, which adds the context information of the testing text into the local PPM statistical model so as to guide the detection of new words. The algorithm focuses on the process of online segmentatien and new word detection which achieves a good effect in the close or opening test, and outperforms some well-known Chinese segmentation system to a certain extent.
文摘A feature extraction, which means extracting the representative words from a text, is an important issue in text mining field. This paper presented a new Apriori and N-gram based Chinese text feature extraction method, and analyzed its correctness and performance. Our method solves the question that the exist extraction methods cannot find the frequent words with arbitrary length in Chinese texts. The experimental results show this method is feasible.
文摘This paper presents a methodology for off-line handwritten Chinese character recognition based on mergence of consecutive segments of adaptive duration. The handwritten Chinese character string is partitioned into a sequence of consecutive segments, which are combined to implement dissimilarity evaluation within a sliding window whose durations are determined adaptively by the integration of shapes and context of evaluations. The average stroke width is estimated for the handwritten Chinese character string, and a set of candidate character segmentation boundaries is found by using the integration of pixel and stroke features. The final decisions on segmentation and recognition are made under minimal arithmetical mean dissimilarities. Experiments proved that the proposed approach of adaptive duration outperforms the method of fixed duration, and is very effective for the recognition of overlapped, broken, touched, loosely configured Chinese characters.
基金Anhui Province College Natural Science Fund Key Project of China(KJ2020ZD77)the Project of Education Department of Anhui Province(KJ2020A0379)。
文摘Objective In tongue diagnosis,the location,color,and distribution of spots can be used to speculate on the viscera and severity of the heat evil.This work focuses on the image analysis method of artificial intelligence(AI)to study the spotted tongue recognition of traditional Chinese medicine(TCM).Methods A model of spotted tongue recognition and extraction is designed,which is based on the principle of image deep learning and instance segmentation.This model includes multiscale feature map generation,region proposal searching,and target region recognition.Firstly,deep convolution network is used to build multiscale low-and high-abstraction feature maps after which,target candidate box generation algorithm and selection strategy are used to select high-quality target candidate regions.Finally,classification network is used for classifying target regions and calculating target region pixels.As a result,the region segmentation of spotted tongue is obtained.Under non-standard illumination conditions,various tongue images were taken by mobile phones,and experiments were conducted.Results The spotted tongue recognition achieved an area under curve(AUC)of 92.40%,an accuracy of 84.30%with a sensitivity of 88.20%,a specificity of 94.19%,a recall of 88.20%,a regional pixel accuracy index pixel accuracy(PA)of 73.00%,a mean pixel accuracy(m PA)of73.00%,an intersection over union(Io U)of 60.00%,and a mean intersection over union(mIo U)of 56.00%.Conclusion The results of the study verify that the model is suitable for the application of the TCM tongue diagnosis system.Spotted tongue recognition via multiscale convolutional neural network(CNN)would help to improve spot classification and the accurate extraction of pixels of spot area as well as provide a practical method for intelligent tongue diagnosis of TCM.
基金supported by National Natural Science Foundation of China (Grant Nos. 40821160550 and 40974057)International Scientific Joint Project of China (Grant No. 2009DFA21280)
文摘The Kunlun Fault, an active fault on the border between the Bayan Har and Kunlun-Qaidam blocks, is one of the major left lateral strike-slip faults in the Tibetan Plateau. Previous research has not reached a consensus on agreeable slip rates along much of its length and the slip rate gradient along the eastern part, both of which play critical roles in a range of models for the eastward extrusion and thickened crust of the Tibetan Plateau. New slip rates have been determined at sites along the eastern part of the Kunlun Fault by dating deposits and measuring atop displaced fluvial terrace risers. Field investigations and interpretation of satellite images reveal geometrical features of the fault and the late Quaternary offset, new earthquake ruptures and surface-rupturing segmentation, from which long-term slip rates and earthquake recurrence intervals on the fault are estimated. The tectonic geomorphology method has determined that the long-term horizontal slip rates on the Tuosuohu, Maqin and Ma- qu segments from west to east are 11.2±1, 9.3±2, and 4.9±1.3 mm/a while their vertical slip rates are 1.2±0.2, 0.7±0.1, and 0.3 mm/a in the late Quaternary. Results indicate that the slip rates regularly decrease along the eastern -300 km of the fault from 〉10 to 〈5 mm/a. This is consistent with the decrease in the gradient such that at the slip rate break point is at the triple point intersection with the transverse fault, which in turn is transformed to the Awancang Fault. The vector decomposition for this tectonic transformation shows that the western and eastern branches of the Awancang Fault fit the slip-partitioning mode. The slip rate of the southwestern wall is 4.6 mm/a relative to the northeastern wall and the slip direction is 112.1°. The mid-eastern part of the Kunlun Fault can be divided into three independent segments by the A＇nyemaqen double restraining bend and the Xigongzhou intersection zone, which compose the surface rupture segmentation indicators for themselves as well as the ending point of the 1937 M7.5 Tuosuohu earthquake. The average recurrence interval of the characteristic earthquakes are estimated to be 500-1000 a, respectively. The latest earthquake ruptures occurred in AD 1937 on the western Tuosuohu segment, as compared to -514-534 a BP on the Maqin segment, and -1055 to 1524 a BP on the Maqu segment. This may indicate a unidirectional migration for surface rupturing earthquakes along the mid-eastern Kunlun Fault related to stress triggered between these segments. Meanwhile, the long-term slip rate is obtained through the single event offset and the recurrence interval, which turn out to be the same results as those determined by the offset tectonic geomorphology method, i.e., the decreasing gradient corresponds to the geometrical bending and the fault＇s intersection with the transverse fault. Therefore, the falling slip rate gradient of the mid-eastern Kunlun Fault is mainly caused by eastward extension of the fault and its intersection with the transverse fault.
基金Fthe National Key Technology R&D Program of China(No.2014BAK15B02)the National Natural Science Foundation of China(No.61202209)
文摘Automatic translation of Chinese text to Chinese Braille is important for blind people in China to acquire information using computers or smart phones. In this paper, a novel scheme of Chinese-Braille translation is proposed. Under the scheme, a Braille word segmentation model based on statistical machine learning is trained on a Braille corpus, and Braille word segmentation is carried out using the statistical model directly without the stage of Chinese word segmentation. This method avoids establishing rules concerning syntactic and semantic information and uses statistical model to learn the rules stealthily and automatically. To further improve the performance, an algorithm of fusing the results of Chinese word segmentation and Braille word segmentation is also proposed. Our results show that the proposed method achieves accuracy of 92.81% for Braille word segmentation and considerably outperforms current approaches using the segmentation-merging scheme.
